MeetAlexis Balayre

AI Engineer specialising in real-time speech AI, LLM systems and production ML. Building Lia Live AI, Acolad's real-time AI interpreting platform, in Paris.

Who am I?

Name: Alexis Balayre

Nationality: French

Location: Paris, France

Degrees: ISEP Engineering Master's Degree | MSc in Computational and Software Techniques in Engineering, Cranfield University

Specialisations: Real-Time Speech AI | LLM Systems | Agentic Systems | Production ML | Software Engineering

Role: AI Engineer at Acolad, building Lia Live AI

AI Engineer specialising in real-time speech AI, LLM systems and production ML, with a dual background in Software Engineering and Data Science. I design, build and operate AI systems end to end, from architecture through deployment. At Acolad I build Lia Live AI, our real-time AI interpreting platform: speech in, interpreted speech out in under a second, across 80+ languages. That covers the streaming ASR, LLM translation and TTS pipelines, the distributed backend behind live sessions, multi-provider routing, and the evaluation framework that settles every model choice on quality and latency. Next: fine-tuning, inference optimisation and on-device deployment. Before that, I applied NLP and generative AI (RAG, GraphRAG) at Dassault Systèmes and did deep learning research with Airbus on computer vision for autonomous aircraft refuelling. I also build in the open, mostly AI tooling and pipelines. And I care about AI security: as these systems take on more autonomy and more sensitive data, making them trustworthy matters as much as making them capable.

Download Resume

Experiences

AI Engineer at Acolad
Sept. 2025 - Present
Acolad is a global leader in language and content solutions, present in 25 countries. As an AI Engineer, I build Lia Live AI, Acolad's real-time AI interpreting platform, owning it end to end from applied speech research to production infrastructure.

- Build the real-time speech pipelines: streaming transcription, LLM translation and streaming voice synthesis, delivering interpreted speech in under a second across 80+ languages, in consecutive and simultaneous modes.
- Design the distributed backend behind live multilingual sessions: a stateless API, a session-affine engine running the audio pipelines and a gateway brokering every provider call, with admission control so stateful real-time sessions scale horizontally over WebRTC, telephony and WebSocket.
- Own the AI layer: config-driven routing across Deepgram, OpenAI, Gemini and Gradium, translation grounded in the running conversation and client glossaries, plus agentic features surfacing clarifications and cultural context.
- Build the evaluation framework that settles every model and provider choice, scoring quality and latency as a single metric against measured human-interpreter delay.
- Run the service in production: incident response, OpenTelemetry and Datadog observability, multi-tenant auth, GDPR-compliant erasure and billing with per-call cost attribution, plus the engineering platform behind it (ADR-driven design, LLM-powered code review in CI).
- Drive the platform's next generation: speech model fine-tuning, inference optimisation and on-device deployment.
Data Scientist at Dassault Systèmes
Jan. 2025 - Jul. 2025
Dassault Systèmes, the 3DEXPERIENCE Company, empowers businesses and individuals with virtual universes to foster sustainable innovation. As a Data Scientist, I worked in the Industry Market Intelligence - Corporate Strategic Planning team to automate and optimise data processes, ultimately driving strategic insights and enabling informed decision-making.

- Accelerated strategic reporting and Market Intelligence by automating data workflows and analysing large-scale datasets (millions of records) using Python and SQL.
- Designed and implemented data-driven solutions leveraging Web Scraping, Natural Language Processing (topic modelling, sentiment analysis), and Generative AI (LLM, RAG, GraphRAG) to extract insights from both structured and unstructured data.
- Built and maintained Competitive Intelligence and monitoring tools to support executive decision-making and strengthen Dassault Systèmes' positioning in its Business sectors.
Data Engineer Freelance at Sidetrade
Oct. 2024 - Nov. 2024
Sidetrade is a leading AI-powered SaaS platform that helps companies enhance working capital and cash flow performance by optimising customer relationship management and automating financial processes.

- Defined the architecture and data workflows for an automated carbon footprint reporting solution, aimed at reducing manual work and improving reporting speed.
- Designed the integration of data from NetSuite, Egencia, Eurécia, and Navan into Power BI to enable dynamic, real-time dashboards with exportable insights.
- Proposed an ETL solution using Microsoft Fabric to streamline the processing of both structured and unstructured data.
- Project was discontinued during implementation due to data privacy constraints related to GDPR compliance.
Research Student at Cranfield University
May 2024 - Sept. 2024
Master's Thesis in collaboration with Airbus, supported by UK Research and Innovation (UKRI) and the Aerospace Technology Institute (ATI), focused on enhancing the efficiency and accuracy of automated ground refueling systems for Smart Airports. Developed an advanced machine learning framework combining the object detection model YOLOv10 and a proposed deep learning sequence model (SizPos-GRU) to accurately predict the future position of commercial aircraft's refueling port in a video stream.
Vice President of the Blockchain Lab at Garage ISEP
Sept. 2022 - Sept. 2023
Garage ISEP is the student association of ISEP dedicated to technology (Blockchain, Artificial Intelligence, ...). Organisation of workshops and conferences to learn and master Blockchain technologies.
Blockchain Developer at CoinShares
Sept. 2022 - Jan. 2023
CoinShares is Europe's largest and oldest crypto asset investment company, managing billions of dollars in assets. Worked within the DeFi team to build a decentralised asset management tool, gaining hands-on experience in Decentralised Finance.

AI Engineer at Acolad
Sept. 2025 - Present
Acolad is a global leader in language and content solutions, present in 25 countries. As an AI Engineer, I build Lia Live AI, Acolad's real-time AI interpreting platform, owning it end to end from applied speech research to production infrastructure.

- Build the real-time speech pipelines: streaming transcription, LLM translation and streaming voice synthesis, delivering interpreted speech in under a second across 80+ languages, in consecutive and simultaneous modes.
- Design the distributed backend behind live multilingual sessions: a stateless API, a session-affine engine running the audio pipelines and a gateway brokering every provider call, with admission control so stateful real-time sessions scale horizontally over WebRTC, telephony and WebSocket.
- Own the AI layer: config-driven routing across Deepgram, OpenAI, Gemini and Gradium, translation grounded in the running conversation and client glossaries, plus agentic features surfacing clarifications and cultural context.
- Build the evaluation framework that settles every model and provider choice, scoring quality and latency as a single metric against measured human-interpreter delay.
- Run the service in production: incident response, OpenTelemetry and Datadog observability, multi-tenant auth, GDPR-compliant erasure and billing with per-call cost attribution, plus the engineering platform behind it (ADR-driven design, LLM-powered code review in CI).
- Drive the platform's next generation: speech model fine-tuning, inference optimisation and on-device deployment.
Data Scientist at Dassault Systèmes
Jan. 2025 - Jul. 2025
Dassault Systèmes, the 3DEXPERIENCE Company, empowers businesses and individuals with virtual universes to foster sustainable innovation. As a Data Scientist, I worked in the Industry Market Intelligence - Corporate Strategic Planning team to automate and optimise data processes, ultimately driving strategic insights and enabling informed decision-making.

- Accelerated strategic reporting and Market Intelligence by automating data workflows and analysing large-scale datasets (millions of records) using Python and SQL.
- Designed and implemented data-driven solutions leveraging Web Scraping, Natural Language Processing (topic modelling, sentiment analysis), and Generative AI (LLM, RAG, GraphRAG) to extract insights from both structured and unstructured data.
- Built and maintained Competitive Intelligence and monitoring tools to support executive decision-making and strengthen Dassault Systèmes' positioning in its Business sectors.
Data Engineer Freelance at Sidetrade
Oct. 2024 - Nov. 2024
Sidetrade is a leading AI-powered SaaS platform that helps companies enhance working capital and cash flow performance by optimising customer relationship management and automating financial processes.

- Defined the architecture and data workflows for an automated carbon footprint reporting solution, aimed at reducing manual work and improving reporting speed.
- Designed the integration of data from NetSuite, Egencia, Eurécia, and Navan into Power BI to enable dynamic, real-time dashboards with exportable insights.
- Proposed an ETL solution using Microsoft Fabric to streamline the processing of both structured and unstructured data.
- Project was discontinued during implementation due to data privacy constraints related to GDPR compliance.
Research Student at Cranfield University
May 2024 - Sept. 2024
Master's Thesis in collaboration with Airbus, supported by UK Research and Innovation (UKRI) and the Aerospace Technology Institute (ATI), focused on enhancing the efficiency and accuracy of automated ground refueling systems for Smart Airports. Developed an advanced machine learning framework combining the object detection model YOLOv10 and a proposed deep learning sequence model (SizPos-GRU) to accurately predict the future position of commercial aircraft's refueling port in a video stream.
Vice President of the Blockchain Lab at Garage ISEP
Sept. 2022 - Sept. 2023
Garage ISEP is the student association of ISEP dedicated to technology (Blockchain, Artificial Intelligence, ...). Organisation of workshops and conferences to learn and master Blockchain technologies.
Blockchain Developer at CoinShares
Sept. 2022 - Jan. 2023
CoinShares is Europe's largest and oldest crypto asset investment company, managing billions of dollars in assets. Worked within the DeFi team to build a decentralised asset management tool, gaining hands-on experience in Decentralised Finance.

Projects

Pupitre: Control Plane for Parallel Claude Code Sessions

A CLI for running many Claude Code sessions in parallel without losing track of the code they write. Each agent works in its own git worktree under a task spec whose scope is enforced by a hook before any edit lands. A conflict radar flags sessions touching the same files, and every merge goes through a gate: build, tests, lint, a scope audit, then technical-debt deltas (duplication, dead code, complexity, coverage) measured against a baseline that only tightens. Shortcuts either get refused or go into a debt ledger with a review-by condition, and every merge writes a decision record. An optional conductor session plans and steers the workers, but the merge stays with the human. Pupitre is built with Pupitre: its own PRs go through its own gate.

TypeScript
Node.js
Claude Code
Git Worktrees
tmux
CLI

agentspine: One Agent Setup for Every Coding Assistant

An npm scaffolder (npx agentspine) that writes conventions, skills and blocking hooks once into .agents/ and wires Claude Code, Codex, opencode, Mistral Vibe and Cursor to read them, so five tools stop drifting across five config directories. Shared hook policies are written once, and a per-tool adapter speaks each host's protocol. A doctor command checks that each block actually took effect. Opt-in skill packs add TDD, diagnosis, planning, a six-area multi-agent code review and a GitHub Actions PR review where the model has no write access to the PR. The output is plain Markdown and POSIX shell, so it works in any stack.

TypeScript
npm
Claude Code
Codex
Cursor
Agent Skills
GitHub Actions

Claude Code Config: Agentic Development Framework

A stack-agnostic Claude Code configuration template that turns agentic coding into a repeatable, reviewed workflow: layered project memory (AGENTS.md + CLAUDE.md), path-scoped convention rules, 34 skills, 12 subagents and 7 deterministic shell hooks enforcing checks no model can skip, such as the quality gate, file naming and never committing to main. It also ships a multi-agent PR review in GitHub Actions: six reviewers report and a validator refutes weak findings. A poster script then writes the result, so the model has no write channel to the PR. Running /adapt-to-project fits it to any repository. This portfolio runs on it.

Claude Code
MCP
Git Worktrees
Shell / Bash
GitHub Actions

AI Daily Summary: Self-Hosted AI News Pipeline

A self-hosted pipeline that reads the day's AI news for you. It ingests Gmail newsletters, RSS feeds, GitHub trending and web crawls, enriches every article with Gemini (relevance, category, summary, tags, embeddings), drops near-duplicates by vector similarity in PostgreSQL + pgvector, and sends one daily HTML newsletter with a Release Radar section and a spoken audio briefing attached. It emails instant alerts when a new model is released and tracks changes on public model leaderboards. A React dashboard, a REST API, a chat endpoint over your own data and an MCP server sit on top of the same database, scheduled with retries and tested in CI.

Python
FastAPI
Gemini
PostgreSQL + pgvector
MCP
React
Docker

AuraHelpdeskGraph: GraphRAG Support Chatbot

A support chatbot that leverages local LLMs, vector similarity search, and knowledge graphs to provide contextual assistance by finding and presenting solutions from historical support tickets.

Python
Graph Database (Neo4j)
Streamlit
openai python client
function calling
GraphRAG
Ollama

View Project

RagDocs: RAG-Powered Chatbot for Technical Documentation

RagDocs is an open-source tool for querying technical documentation using local LLMs. It indexes documents into a Milvus vector store and answers questions with Retrieval-Augmented Generation (RAG), so documentation stays private and queries run without external API costs. Built with Next.js, FastAPI, LlamaIndex, and Ollama, and deployable via Docker.

Python
Vector Database (Milvus)
Next.js
FastAPI
LLamaIndex
Ollama
Docker

View Project

Speech Models Knowledge Hub

A curated, opinionated knowledge base of open-source speech AI, organised by domain: ASR, TTS, speech-to-speech, speech LLMs and diarization. Each domain covers tools and libraries, notable models, datasets, benchmarks and leaderboards, inference and optimisation, fine-tuning and RL recipes, and key papers. It is the reading list behind my day-to-day work on real-time speech translation.

ASR
TTS
Speech-to-Speech
Speech LLMs
Diarization

View Project

Agents Knowledge Hub

The companion hub for LLM agents: frameworks and multi-agent orchestration, protocols (MCP, A2A, tool calling), memory and context management, evaluation harnesses and leaderboards, and safety (guardrails, sandboxing, permissions). Same structure as the speech hub, with a contribution guide and curation rules.

Agent Frameworks
MCP
A2A
Agent Evals
AI Safety

View Project

Master's Thesis: Future Position Prediction for Pressure Refuelling Port of Commercial Aircraft:

This thesis develops a deep learning framework to predict the future position of aircraft refuelling ports, enhancing automated refuelling systems. The approach integrates a fine-tuned YOLOv10 model for detection with the proposed 'SizPos-GRU' sequence model, which captures temporal and spatial relationships from video frames using an encoder-attention-decoder architecture. Results show that the SizPos-GRU model outperforms other models, achieving an Average Displacement Error (ADE) of 4.28% and a Final Displacement Error (FDE) of 9.18% when using 30 past frames to predict 60 future frames. For predictions using 15 past frames to predict 30 future frames, the model achieved an ADE of 2.15% and an FDE of 4.83%. These results demonstrate significant improvements in prediction accuracy, proving the framework’s effectiveness in automating and enhancing aircraft refuelling operation.

Python
PyTorch Lightning
OpenCV
OpenAI API
Label Studio
Docker
YOLOv10

View Project

GPTAggregator

GPTAggregator is a Python-based application that provides a unified interface for interacting with various large language models (LLMs) via their respective APIs. The project is designed to be user-friendly and easily extensible, making it a powerful tool for developers, researchers and anyone interested in exploiting the capabilities of large language models. GPTAggregator makes it possible to switch seamlessly from one model to another within the same conversation, centralise conversation storage, automatically optimise messages, and much more.

Python
Streamlit
Hugging Face Transformers
OpenAI API
MistralAI API
Anthropic API
Groq API

View Project

AI-Powered Meeting Summarizer

The AI-Powered Meeting Summarizer is a Gradio-powered application that converts audio recordings of meetings into transcripts and provides concise summaries using whisper.cpp for audio-to-text conversion and Ollama for text summarisation. This tool is ideal for quickly extracting key points, decisions, and action items from meetings.

Python
Gradio
whisper.cpp
Ollama

View Project

Group Project: Deep Learning for Turbulence Modelling

This project focuses on the innovative integration of machine learning with computational fluid dynamics (CFD) to address the limitations of traditional turbulence models. By incorporating Physically Informed Neural Networks (PINNs) and employing the Sparse Identification of Nonlinear Dynamical Systems (PySINDy) approach, we aim to improve the accuracy and efficiency of turbulent flow simulations. This interdisciplinary effort aims to harness the power of high-performance computing to revolutionise the predictive modelling of fluid dynamics.

Python
PyTorch Lightning
PySINDy
PINN
HPC
AWS

View Project

Chest X-Ray Abnormalities Detection with Faster R-CNN

This project leverages the Faster R-CNN model with a ResNet-50 backbone, implemented using PyTorch Lightning, for the detection and localisation of thoracic abnormalities in chest X-ray images.

Python
PyTorch Lightning
Faster R-CNN
ResNet-50

View Project

COVID-19 Data Analysis Project Using Apache Spark

This project harnesses Big Data and Machine Learning technologies to analyse the global impact of the COVID-19 pandemic. Utilising Apache Spark, it processes extensive datasets of COVID-19 cases, uncovering insights into the virus's spread and effects.

Apache Spark
Apache Airflow
Scikit-learn
Pyspark
Pandas
Seaborn
Matplotlib

View Project

Cloud Computing and IoT for Environmental Monitoring Project

This project integrates Cloud Computing with the Internet of Things (IoT) for comprehensive environmental monitoring, with a focus on air quality analysis. Utilising Apache Spark and Amazon Timestream, it manages large volumes of data from IoT sensors to calculate the Air Quality Index (AQI) accurately, offering insights into environmental conditions.

Apache Spark
Amazon Timestream
AWS EC2
Grafana

View Project

PriceSense: Correlating News Sentiment with Stock Prices

This project examines the relationship between financial news sentiment and stock market prices using two data pipelines. The first pipeline uses LocalStack to mimic Amazon S3 for data storage and messaging, while the second utilises Apache Kafka for real-time streaming and message exchange. Both pipelines process financial news and stock price data, calculate sentiment scores, merge this data, and then index it into Elasticsearch for analysis and visualisation.

Apache Spark
Apache Kafka
Apache Airflow
Elasticsearch
Kibana
LocalStack
AWS

View Project

Skills

CoreDaily, production-gradeWorkingSolid, used in real projectsFamiliarSome hands-on experience

Programming Languages

Core

TypeScriptPythonSQL

Working

SolidityC/C++Shell / Bash

Familiar

JavaRust

Generative AI & LLMs

Core

OpenAIGeminiClaudeHugging Face Transformers

Working

vLLMOllamaLangChainLangGraphLlamaIndex

Speech & Real-Time AI

Core

DeepgramGradiumLiveKit

AI & Data Intelligence

Core

NumPypandasScikit-learnMatplotlibPyTorch Lightning

Working

XGBoost / LightGBMPolarsPlotlyspaCyMLflow

Familiar

OpenCV

AI Dev Workflow

Core

Claude CodeMCP

Working

Git Worktrees

Databases

Core

MongoDBPostgreSQLElasticsearch

Working

OpenSearchNeo4jRedisMilvusChroma

Data Engineering Tools

Core

Apache Airflow

Working

Apache Spark

Familiar

Apache Kafka

Frontend

Core

Next.jsTailwindCSSStreamlit

Working

Vue.js / NuxtGradio

Backend

Core

Node.js / NestJSFastAPI

Hosting & Cloud Services

Core

AWS

Working

RunPodCloudflare

Familiar

Azure

Server Management & DevOps

Core

Docker

Working

Git / GitHub Actions / CI/CDLinux (Ubuntu, CentOS)Kubernetes

Familiar

NGINX

Other Tools

Core

LaTeX

Hackathons

ETHGlobal ETHOnline 2023 Winner
Oct. 2023
ETHOnline is a three week long online hackathon with over $200,000 USD in prizes as well as a series of curated summits, celebrating some of the most significant happenings & learnings from the past 12 months in web3. Enigma introduces the Secret NFTs standard: a unique dual URI approach. Each NFT showcases a public and a private layer. Only owners have full access. From art to memberships, prioritising privacy in the digital domain is paramount. Enigma won 2 prizes at the 2023 ETHGlobal ETHOnline hackathon : "The Graph — Best New Subgraph or Substream" and "Scroll — Pool Prize".
Chainlink Spring 2022 Winner
May 2022
Hackathon to build the next generation of Web3 apps with $500K+ in prizes. Winner of Chainlink Top Quality Projects.
ETHGlobal HackMoney 2022 Winner
May 2022
World's largest DeFi hackathon. Sleepn is a decentralised sleep tracking application that allows you to earn money by sleeping. Sleepn won 2 prizes at the 2022 ETHGlobal HackMoney hackathon : "Polygon — Best App" and "Superfluid — Best Use With Another Partner".
Finalist in Devoteam's Cyber Hackathon
Oct. 2021 - Nov. 2021
Finalist in the 'Devogame' cybersecurity competition organised by Devoteam out of more than 3,800 entrants. Proposed a system for verifying a company's logs using a private blockchain and a consensus system based on private keys.

ETHGlobal ETHOnline 2023 Winner
Oct. 2023
ETHOnline is a three week long online hackathon with over $200,000 USD in prizes as well as a series of curated summits, celebrating some of the most significant happenings & learnings from the past 12 months in web3. Enigma introduces the Secret NFTs standard: a unique dual URI approach. Each NFT showcases a public and a private layer. Only owners have full access. From art to memberships, prioritising privacy in the digital domain is paramount. Enigma won 2 prizes at the 2023 ETHGlobal ETHOnline hackathon : "The Graph — Best New Subgraph or Substream" and "Scroll — Pool Prize".
Chainlink Spring 2022 Winner
May 2022
Hackathon to build the next generation of Web3 apps with $500K+ in prizes. Winner of Chainlink Top Quality Projects.
ETHGlobal HackMoney 2022 Winner
May 2022
World's largest DeFi hackathon. Sleepn is a decentralised sleep tracking application that allows you to earn money by sleeping. Sleepn won 2 prizes at the 2022 ETHGlobal HackMoney hackathon : "Polygon — Best App" and "Superfluid — Best Use With Another Partner".
Finalist in Devoteam's Cyber Hackathon
Oct. 2021 - Nov. 2021
Finalist in the 'Devogame' cybersecurity competition organised by Devoteam out of more than 3,800 entrants. Proposed a system for verifying a company's logs using a private blockchain and a consensus system based on private keys.

Education

Cranfield University - MSc in Computational and Software Techniques in Engineering
Sept. 2023 - Sept. 2024
MSc at Cranfield University as part of a double degree programme with ISEP.

Cranfield University, located in the UK, is a distinguished public institution exclusively dedicated to postgraduate education and research. It boasts a specialisation in science, engineering, technology, and management, holding the unique distinction of being the UK's sole postgraduate-only university.

Modules studied:
- Machine Learning and Big Data
- Artificial Intelligence
- High Performance Technical Computing
- Cloud Computing
- Small-Scale Parallel Programming
- Management for Technology
ISEP - Engineering Master Degree
2021 - 2024
Engineering cycle at ISEP in Paris. Specialisation in Data Intelligence.

ISEP is a French digital engineering school located in Paris. It trains general engineers in the key fields of digital technology: IT & Cybersecurity - Electronics & Robotics - Telecommunications & Internet of Things - Imaging - Artificial Intelligence.
CVUT - Academic Semester Abroad
Feb. 2021 - Jun. 2021
Academic semester in English at the Czech Technical University in Prague.

Modules studied:
- Telecommunication Systems and Networks
- Introduction to Cyber Security
- Environmental Engineering
- Discrete mathematics
- Programming
- English
ISEP - International Integrated Cycle (CII)
2019 - 2021
Preparatory years at the ISEP engineering school in Paris.

The CII follows a programme specific to ISEP, balanced across three teaching areas: Fundamental Digital Sciences | Techniques & Technologies | Languages, Cultures, Humanities and Sustainable Development. It includes an international semester from the second year.

Cranfield University - MSc in Computational and Software Techniques in Engineering
Sept. 2023 - Sept. 2024
MSc at Cranfield University as part of a double degree programme with ISEP.

Cranfield University, located in the UK, is a distinguished public institution exclusively dedicated to postgraduate education and research. It boasts a specialisation in science, engineering, technology, and management, holding the unique distinction of being the UK's sole postgraduate-only university.

Modules studied:
- Machine Learning and Big Data
- Artificial Intelligence
- High Performance Technical Computing
- Cloud Computing
- Small-Scale Parallel Programming
- Management for Technology
ISEP - Engineering Master Degree
2021 - 2024
Engineering cycle at ISEP in Paris. Specialisation in Data Intelligence.

ISEP is a French digital engineering school located in Paris. It trains general engineers in the key fields of digital technology: IT & Cybersecurity - Electronics & Robotics - Telecommunications & Internet of Things - Imaging - Artificial Intelligence.
CVUT - Academic Semester Abroad
Feb. 2021 - Jun. 2021
Academic semester in English at the Czech Technical University in Prague.

Modules studied:
- Telecommunication Systems and Networks
- Introduction to Cyber Security
- Environmental Engineering
- Discrete mathematics
- Programming
- English
ISEP - International Integrated Cycle (CII)
2019 - 2021
Preparatory years at the ISEP engineering school in Paris.

The CII follows a programme specific to ISEP, balanced across three teaching areas: Fundamental Digital Sciences | Techniques & Technologies | Languages, Cultures, Humanities and Sustainable Development. It includes an international semester from the second year.

MeetAlexis Balayre

Who am I?

Experiences

AI Engineer at Acolad

Data Scientist at Dassault Systèmes

Data Engineer Freelance at Sidetrade

Research Student at Cranfield University

Vice President of the Blockchain Lab at Garage ISEP

Blockchain Developer at CoinShares

AI Engineer at Acolad

Data Scientist at Dassault Systèmes

Data Engineer Freelance at Sidetrade

Research Student at Cranfield University

Vice President of the Blockchain Lab at Garage ISEP

Blockchain Developer at CoinShares

Projects

Pupitre: Control Plane for Parallel Claude Code Sessions

Read more on the blog

agentspine: One Agent Setup for Every Coding Assistant

Read more on the blog

Claude Code Config: Agentic Development Framework

Read more on the blog

AI Daily Summary: Self-Hosted AI News Pipeline

Read more on the blog

AuraHelpdeskGraph: GraphRAG Support Chatbot

RagDocs: RAG-Powered Chatbot for Technical Documentation

Speech Models Knowledge Hub

Agents Knowledge Hub

Master's Thesis: Future Position Prediction for Pressure Refuelling Port of Commercial Aircraft:

GPTAggregator

AI-Powered Meeting Summarizer

Group Project: Deep Learning for Turbulence Modelling

Chest X-Ray Abnormalities Detection with Faster R-CNN

COVID-19 Data Analysis Project Using Apache Spark

Cloud Computing and IoT for Environmental Monitoring Project

PriceSense: Correlating News Sentiment with Stock Prices

Skills

Programming Languages

Generative AI & LLMs

Speech & Real-Time AI

AI & Data Intelligence

AI Dev Workflow

Databases

Data Engineering Tools

Frontend

Backend

Hosting & Cloud Services

Server Management & DevOps

Other Tools

Hackathons

ETHGlobal ETHOnline 2023 Winner

Chainlink Spring 2022 Winner

ETHGlobal HackMoney 2022 Winner

Finalist in Devoteam's Cyber Hackathon

ETHGlobal ETHOnline 2023 Winner

Chainlink Spring 2022 Winner

ETHGlobal HackMoney 2022 Winner

Finalist in Devoteam's Cyber Hackathon

Education

Cranfield University - MSc in Computational and Software Techniques in Engineering

ISEP - Engineering Master Degree

CVUT - Academic Semester Abroad

ISEP - International Integrated Cycle (CII)

Cranfield University - MSc in Computational and Software Techniques in Engineering

ISEP - Engineering Master Degree

CVUT - Academic Semester Abroad

ISEP - International Integrated Cycle (CII)